Mistral: Mistral Small 3

Mistral Small 3 is a text-only model from Mistral AI with a 32,768-token context window and a maximum output of 16,384 tokens. It does not support tool use or reasoning modes, and structured output support is unconfirmed. Those constraints make it a straightforward text-in, text-out option with no built-in function-calling or multi-step reasoning capabilities. At $0.05 per million input tokens and $0.08 per million output tokens, it sits at the budget end of the market, which is its clearest argument for consideration. However, benchmark coverage is thin, with a blended score of 28.8 drawn from only one benchmark, so quality comparisons against other models should be treated cautiously. Teams running high-volume, cost-sensitive text tasks who can tolerate limited benchmark evidence may find it worth testing, but buyers who need tool use, structured output, or well-validated performance should look elsewhere.